jarvis-assistant-vocal

Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.

Runs with mockssource: GitHubPythonMITcommit 32faa786155a

Python, MIT licensed. The project labels itself: anthropic claude, browser automation, home automation, jarvis, local ai, mcp, mcp server and obs.

jarvis-assistant-vocal runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Jarvis installs cleanly, its 181-test suite passes (4 Windows-only cases skipped), the Signal Matin pipeline emits valid A4 PDFs in all three density modes without overflow, and the OpenAI provider answers through a schema-correct local mock; only a physical microphone is missing.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$1.30 (measured)
recorded runs
1
last tested
stars
571
forks
154
open issues
12
watchers
13
size
1 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing jarvis-assistant-vocal, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Signal Matin compact page overflow (content 1009px vs 975px), project PDF guard rejected page 325 minutes
  • sounddevice failed: PortAudio library not found; satellite module unittest couldn't import20 minutes
  • ctypes.windll import crashed tools.souris on Linux5 minutes
  • os.startfile missing on Linux in tools/spotify.py and tools/systeme.py5 minutes
  • Playwright Chromium missing (playwright install)5 minutes
  • 4 unittest errors patching Windows-only os.startfile on Linux5 minutes
Install time
1 minutes
Cold machine to finish
36 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
uv run python -m unittest discover -s tests -> Ran 181 tests, OK (skipped=4); uv run python scripts/doctor.py -> Bilan 15 OK, 7 avertissements, 1 probleme (aucun micro detecte); mock OpenAI client responses.create -> 'Bonjour ! Le test mock fonctionne.'; generer_pdf compact/standard/extended -> 4/8/8 A4 pages, internal overflow guard passed
Model tokens used
6,446,976
Exact commit tested
32faa786155a
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

**Errors record**
- `ctypes.windll` on Linux → guard + None checks (fix).
- `os.startfile` missing on Linux in 2 modules → try/exist fallback to `xdg-open` (fix).
- `sounddevice` PortAudio missing in container → userland `.so` shim in `$HOME` + guarded imports (…
- Chromium missing for Playwright → `playwright install chromium` (fix).
- Signal Matin compact page overflow → truncate 2→1 items in digest/recommendations (fix).
**Verification**
- `uv run python -m unittest discover -s tests` → `Ran 181 tests ... OK (skipped=4)`.
- `generer_pdf` for compact/standard/extended → 4/8/8 pages, each `594.96 x 841.92` (A4), passes th…
- `scripts/doctor.py` → `Bilan : 15 OK, 7 avertissement(s), 1 probleme(s)` (audible hardware only).
- Mock LLM → response text returned.
**Final state** — Jarvis installs, the test suite passes (177/181, 4 Windows-only skips), the Signa…

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Installed in 1 minute.
  • Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.001.30

Topics (from GitHub)

anthropic-claudebrowser-automationhome-automationjarvislocal-aimcpmcp-serverobsollamaphilips-hueplaywrightpythontwiliovoice-assistantwhisper

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/jarvis-assistant-vocal.svg)](https://argusic.com/subject/jarvis-assistant-vocal)

Questions

Does jarvis-assistant-vocal run?
jarvis-assistant-vocal runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test jarvis-assistant-vocal?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 32faa786155a. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test jarvis-assistant-vocal?
The run that produced this verdict cost $1.30: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does jarvis-assistant-vocal take to install?
1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does jarvis-assistant-vocal need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing jarvis-assistant-vocal?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for jarvis-assistant-vocal?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion